LFM2.5 2.6B Heretic Abliterated needs about 4.2 GB of memory at Q4_K_M (a 1.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 7 quants, from 1.4 GB (Q3_K_M) to 2.9 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 8.1 GB.
2.6B LFM2.5 model for on‑device agentic tasks
LFM2.5 2.6B Heretic Abliterated is a 2.69 billion‑parameter text‑only model with a 128 K context window. It is optimized for local inference and supports native tool calling and multi‑step instruction following.
Good at
- Agentic tool use
- Long‑context reasoning
- Multi‑step instruction following
Limits
- No vision support
- Uncensored content may violate policy
- Requires 8 k context for memory estimates
Best for
- Local agentic workflows
- Tool‑based data extraction
- RAG with long documents
Who it’s for. Developers building local agents that need large context and tool calling. Suitable for on‑device inference on CPUs or GPUs with enough VRAM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q3_K_M | 1.4 GB | 3.9 GB | Fits | Get file → | |
| Q4_K_S | 1.6 GB | 4.1 GB | Fits | Get file → | |
| Q4_K_M | 1.7 GB | 4.2 GB | Fits | Get file → | |
| Q5_K_S | 1.9 GB | 4.4 GB | Fits | Get file → | |
| Q5_K_M | 1.9 GB | 4.5 GB | Fits | Get file → | |
| Q6_K | 2.2 GB | 4.7 GB | Fits | Get file → | |
| Q8_0 | 2.9 GB | 5.4 GB | Fits | Get file → |
For 8 GB VRAM, Q4_K_M (1.67 GB) or Q5_K_M (1.94 GB) are recommended. Q3_K_M (1.37 GB) fits tighter budgets but with lower quality. Q6_K (2.22 GB) and Q8_0 (2.87 GB) provide higher fidelity at higher memory cost.
What GPU do you need for LFM2.5 2.6B Heretic Abliterated?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is Q3_K_M (1.4 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (2.9 GB file, about 5.4 GB in use).
Which LFM2.5 2.6B Heretic Abliterated quant should you choose?
Q4_K_M is the usual starting point for LFM2.5 2.6B Heretic Abliterated: it balances file size and quality well. Here it is a 1.7 GB file.
The Q8_0 file is 2.9 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q3_K_M at 1.4 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about LFM2.5 2.6B Heretic Abliterated
How much VRAM does LFM2.5 2.6B Heretic Abliterated need?
About 4.2 GB at Q4_K_M with an 8K context window. That is the 1.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run LFM2.5 2.6B Heretic Abliterated on an 8 GB GPU?
Yes, with Q8_0: the 2.9 GB file needs about 5.4 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of LFM2.5 2.6B Heretic Abliterated GGUF?
It depends on the quant: Q3_K_M is 1.4 GB, Q4_K_S is 1.6 GB, Q4_K_M is 1.7 GB, Q5_K_S is 1.9 GB, Q5_K_M is 1.9 GB, Q6_K is 2.2 GB and 1 more.
What context length does LFM2.5 2.6B Heretic Abliterated support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 2.0 GB at 8K and 8.1 GB at 32K.
Where can I download LFM2.5 2.6B Heretic Abliterated GGUF?
The files are on Hugging Face in the Abiray/LFM2.5-2.6B-Heretic-Abliterated-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does LFM2.5 2.6B Heretic Abliterated use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run LFM2.5 2.6B on 8 GB VRAM?
Yes, Q4_K_M or Q5_K_M quantizations fit within 8 GB VRAM, with estimated memory usage around 4.2–4.5 GB at 8 k context.
Does the model support vision?
No, it is a text‑only model and does not process images.
Is the model licensed for commercial use?
It is released under the Apache‑2.0 license, allowing commercial deployment.